Update app.py

app.py

@@ -4,11 +4,13 @@ from huggingface_hub import InferenceClient
 client = InferenceClient(model="https://zgg3nzdpswxy4a-80.proxy.runpod.net")
 
 def inference(message, history):
-    partial_message = ""
-    for token in client.text_generation(message, max_new_tokens=256, stream=False, 
-                                        temperature=0.5, do_sample=True, top_p=0.9):
-        partial_message += token
-        yield partial_message
+    return client.text_generation(message, max_new_tokens=256, stream=False, 
+                                        temperature=0.5, do_sample=True, top_p=0.9)
+    # partial_message = ""
+    # for token in client.text_generation(message, max_new_tokens=256, stream=False, 
+    #                                     temperature=0.5, do_sample=True, top_p=0.9):
+    #     partial_message += token
+    #     yield partial_message
 
 gr.ChatInterface(
     inference,